Diversity-based niche genetic algorithm for bi-objective mixed fleet vehicle routing problem with time window

With the gradual introduction of electric vehicles, logistics systems currently rely primarily on mixed fleets of electric and conventional vehicles to carry out distribution tasks. Given the differences in pollution emissions between electric and traditional vehicles, as well as the additional cons...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 37; no. 17; pp. 11479 - 11499
Main Authors: Du, Shengli, Li, Shilong, Han, Honggui, Qiao, Junfei
Format: Journal Article
Language:English
Published: London Springer London 01.06.2025
Springer Nature B.V
Subjects:
Artificial Intelligence
Carbon
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Electric vehicles
Emissions
Genetic algorithms
Image Processing and Computer Vision
Logistics
Original Article
Probability and Statistics in Computer Science
Vehicle routing
Mixed fleet vehicle routing problem
Niche genetic algorithm
Partial variable-length coding method
Customer satisfaction
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the gradual introduction of electric vehicles, logistics systems currently rely primarily on mixed fleets of electric and conventional vehicles to carry out distribution tasks. Given the differences in pollution emissions between electric and traditional vehicles, as well as the additional consideration of charging routes for electric vehicles, a reasonable formation of the two types of vehicles will effectively reduce carbon emissions during distribution and enhance the economic benefits of the logistics system. This article establishes a bi-objective model aimed at minimizing carbon emissions and travel costs while maximizing customer satisfaction. A diversity-based niche genetic algorithm is proposed to better explore distribution schemes using different kinds of mixed fleets. Firstly, a partial variable-length coding method is introduced to facilitate chromosome generation in the model. Secondly, a diversity evaluation based on entropy is proposed to search for various distribution schemes. Finally, niche elitism and niche tournament selection are proposed, and the crossover and mutation operators are correspondingly improved for the algorithm. The experiments suggest that the bi-objective model is well-established, demonstrating the anticipated conflict between the two objectives. Additionally, the diversity-based niche genetic algorithm is shown to be effective in achieving a wider variety of distribution schemes.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-025-11132-6